Update app.py

app.py

@@ -62,7 +62,8 @@ def generate(
     if max_new_tokens > MAX_MAX_NEW_TOKENS:
         raise ValueError
 
-    history = history_with_input[:-1]
+    #history = history_with_input[:-1]
+    history = []    
     generator = run(message, history, system_prompt, max_new_tokens, temperature, top_p, top_k)
     try:
         first_response = next(generator)